CN109658172A - A kind of commercial circle recommended method calculates unit and storage medium - Google Patents
A kind of commercial circle recommended method calculates unit and storage medium Download PDFInfo
- Publication number
- CN109658172A CN109658172A CN201711328541.7A CN201711328541A CN109658172A CN 109658172 A CN109658172 A CN 109658172A CN 201711328541 A CN201711328541 A CN 201711328541A CN 109658172 A CN109658172 A CN 109658172A
- Authority
- CN
- China
- Prior art keywords
- commercial circle
- brand
- source
- shops
- association
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
A kind of commercial circle recommended method calculates unit and storage medium, wherein the described method includes: determine the commercial circle where the existing shops of target brand, liveness of the acquisition existing shops of target brand in each commercial circle;Determine that the source commercial circle of the existing shops of target brand, source commercial circle are that liveness is greater than the commercial circle where the shops of first threshold in the existing shops of target brand;The similarity of calculating source commercial circle and commercial circle to be recommended, the commercial circle to be recommended for determining that similarity is greater than second threshold is candidate commercial circle corresponding with source commercial circle;First degree of association that target brand and brand to be associated in the commercial circle of source are calculated according to the behavioral data of user in the commercial circle of source determines that first degree of association is greater than the brand to be associated of third threshold value for the association brand of target brand in the commercial circle of source;Second degree of association that brand and target brand are associated in candidate commercial circle is calculated, the candidate commercial circle for determining that second degree of association is greater than the 4th threshold value is target corresponding with source commercial circle commercial circle.
Description
Technical field
This application involves network technique field, in particular to a kind of commercial circle recommended method calculates unit and storage Jie
Matter.
Background technique
In recent years, data calculate and the technologies such as relevant proposed algorithm are being people with the development of information technology
The every field of life provides powerful decision support, and with the continuous improvement of inhabitant's consumption level, commercial store is more and more,
Commercial circle recommendation is more and more important for the addressing of commercial store, and the prior art carries out commercial circle and recommends to rely on personal experience more, still
The experience of different people difference, it is uncertain very high, it intuitively cannot accurately find most suitable commercial circle and be recommended.
Summary of the invention
In view of the above problems, it this application provides a kind of commercial circle recommended method, calculating unit and storage medium, mentions
The accuracy that high commercial circle is recommended.
On the one hand, the embodiment of the present application provides a kind of commercial circle recommended method, comprising:
It determines the commercial circle where the existing shops of target brand, acquires the existing shops of target brand enlivening in each commercial circle
Degree;
Determine that the source commercial circle of the existing shops of target brand, the source commercial circle are liveness in the existing shops of target brand
Greater than the commercial circle where the shops of first threshold;
The similarity for calculating the source commercial circle and commercial circle to be recommended determines that the similarity is greater than the to be recommended of second threshold
Commercial circle is candidate commercial circle corresponding with the source commercial circle;
Target brand and brand to be associated in the source commercial circle are calculated according to the behavioral data of user in the source commercial circle
First degree of association, the brand to be associated for determining that first degree of association is greater than third threshold value is the target product in the source commercial circle
The association brand of board;
Second degree of association for calculating the association brand and the target brand in the candidate commercial circle, determines described second
The candidate commercial circle that the degree of association is greater than the 4th threshold value is target commercial circle corresponding with the source commercial circle.
In the application one schematical embodiment, the similarity for calculating the source commercial circle and commercial circle to be recommended
Include:
Obtain the characteristic value of the source commercial circle and commercial circle to be recommended, wherein the characteristic value includes: that the shop of commercial circle is divided equally
Cloth, shop is equal, shops's number, environment, service, shops's star, shops's number of reviews, shops's business hours and/or non-food brand point
Cloth;
By the feature value vector of the source commercial circle and commercial circle to be recommended, feature vector is obtained;
Establish similarity calculation;
According to the feature vector of the source commercial circle, the feature vector of the commercial circle to be recommended and the similarity calculation mould
Type calculates the similarity of the source commercial circle Yu the commercial circle to be recommended.
In the application one schematical embodiment, the similarity calculation are as follows:
Wherein, ρx,yThe similarity of expression source commercial circle X and commercial circle Y to be recommended, X and Y indicate source commercial circle X and commercial circle Y to be recommended
Feature vector,WithThe mean value of expression source commercial circle X and Y feature vector in commercial circle to be recommended.
It is described to calculate target brand and brand to be associated in the source commercial circle in one illustrative embodiments of the application
First degree of association include:
Obtain the first number of users for entering the existing shops of target brand in the commercial circle of source;
It obtains and enters the existing shops of target brand and the second user number into brand shops to be associated in the commercial circle of source;
Establish the first calculation of relationship degree model;
According to first number of users, the second user number and the first calculation of relationship degree model, described is determined
One degree of association.
In one illustrative embodiments of the application, the first calculation of relationship degree model are as follows:
Wherein, P (A, B) indicates first degree of association of target brand A and brand B to be associated in the commercial circle of source, frq (A, B) table
Show enter source commercial circle in target brand A shops and enter source commercial circle in brand B to be associated shops second user number, N be into
Enter the first number of users of target brand A shops in the commercial circle of source.
In one illustrative embodiments of the application, it is described calculate in the candidate commercial circle association brand with it is described
Second degree of association of target brand includes:
The second user number and candidate commercial circle are obtained, and the second user number is normalized;
Establish the second calculation of relationship degree model;
According to the second user number and the second calculation of relationship degree model of the normalized, calculates second and close
Connection degree.
In one illustrative embodiments of the application, the second calculation of relationship degree model are as follows:
Wherein,Indicate second degree of association of n association brand and target brand in i-th of candidate commercial circle c;ciTable
Show i-th of candidate commercial circle c;K indicates the quantity that there is association brand in i-th of candidate commercial circle c;f(A,Bj) indicate warp
The shops into target brand A and entrance association brand B after crossing normalizedjShops second user number.
In one illustrative embodiments of the application, liveness packet of the existing shops of target brand in each commercial circle
It includes:
The turnover, the volume of the flow of passengers and/or the network click amount of each shops of the target brand.
On the other hand, the application also provides a kind of commercial circle recommendation apparatus, comprising:
Acquisition module acquires the existing shops of target brand each for determining the commercial circle where the existing shops of target brand
The liveness of a commercial circle;
Source commercial circle determining module, for determining that the source commercial circle of the existing shops of target brand, the source commercial circle are target
Liveness is greater than the commercial circle where the shops of first threshold in the existing shops of brand;
Candidate commercial circle determining module determines described similar for calculating the similarity of the source commercial circle and commercial circle to be recommended
The commercial circle to be recommended that degree is greater than second threshold is candidate commercial circle corresponding with the source commercial circle;
It is associated with brand determining module, for calculating mesh in the source commercial circle according to the behavioral data of user in the source commercial circle
First degree of association for marking brand and brand to be associated, the brand to be associated for determining that first degree of association is greater than third threshold value is institute
State the association brand of the target brand in the commercial circle of source;
Target commercial circle determining module, for calculating the of the association brand and the target brand in the candidate commercial circle
Two degrees of association, the candidate commercial circle for determining that second degree of association is greater than the 4th threshold value is target quotient corresponding with the source commercial circle
Circle.
In the application one schematical embodiment, candidate commercial circle determining module further include:
First candidate commercial circle determines submodule, for obtaining the characteristic value of the source commercial circle and commercial circle to be recommended, wherein
The characteristic value includes: that the shop of commercial circle is distributed, and shop is equal, shops's number, environment, service, shops's star, shops's number of reviews, door
Shop business hours and/or non-food brand distribution;
Second candidate commercial circle determines submodule, for by the feature value vector of the source commercial circle and commercial circle to be recommended,
Obtain feature vector;
Third candidate commercial circle determines submodule, for establishing similarity calculation;
4th candidate commercial circle determines submodule, for according to the feature vector of the source commercial circle, the commercial circle to be recommended
Feature vector and the similarity calculation calculate the similarity of the source commercial circle Yu the commercial circle to be recommended.
In the application one schematical embodiment, the similarity calculation are as follows:
Wherein, ρx,yThe similarity of expression source commercial circle X and commercial circle Y to be recommended, X and Y indicate source commercial circle X and commercial circle Y to be recommended
Feature vector,WithThe mean value of expression source commercial circle X and Y feature vector in commercial circle to be recommended.
In the application one schematical embodiment, the association brand determining module includes:
First association brand determines submodule, for obtaining the first user for entering the existing shops of target brand in the commercial circle of source
Number;
Second association brand determines submodule, for obtain enter source commercial circle in the existing shops of target brand and enter to
It is associated with the second user number of brand shops;
Third association brand determines submodule, for establishing the first calculation of relationship degree model;
4th association brand determines submodule, for according to first number of users, the second user number and described the
One calculation of relationship degree model determines first degree of association.
In the application one schematical embodiment, the first calculation of relationship degree model are as follows:
Wherein, P (A, B) indicates first degree of association of target brand A and brand B to be associated in the commercial circle of source, frq (A, B) table
Show enter source commercial circle in target brand A shops and enter source commercial circle in brand B to be associated shops second user number, N be into
Enter the first number of users of target brand A shops in the commercial circle of source.
In one illustrative embodiments of the application, target commercial circle determining module includes:
First object commercial circle determines submodule, for obtaining the second user number and candidate commercial circle, and by described second
Number of users is normalized;
Second target commercial circle determines submodule, for establishing the second calculation of relationship degree model;
Third target commercial circle determines submodule, for according to the second user number of the normalized and described
Two calculation of relationship degree models calculate second degree of association.
In one illustrative embodiments of the application, the second calculation of relationship degree model are as follows:
Wherein,Indicate second degree of association of n association brand and target brand in i-th of candidate commercial circle c;ciTable
Show i-th of candidate commercial circle c;K indicates the quantity that there is association brand in i-th of candidate commercial circle c;f(A,Bj) indicate warp
The shops into target brand A and entrance association brand B after crossing normalizedjShops second user number.
In one illustrative embodiments of the application, liveness packet of the existing shops of target brand in each commercial circle
It includes:
The turnover, the volume of the flow of passengers and/or the network click amount of each shops of the target brand.
Another aspect, the application also provide a kind of calculating equipment, including memory, processor and storage are on a memory simultaneously
The computer instruction that can be run on a processor, the processor perform the steps of when executing described instruction
It determines the commercial circle where the existing shops of target brand, acquires the existing shops of target brand enlivening in each commercial circle
Degree;
Determine that the source commercial circle of the existing shops of target brand, the source commercial circle are liveness in the existing shops of target brand
Greater than the commercial circle where the shops of first threshold;
The similarity for calculating the source commercial circle and commercial circle to be recommended determines that the similarity is greater than the to be recommended of second threshold
Commercial circle is candidate commercial circle corresponding with the source commercial circle;
Target brand and brand to be associated in the source commercial circle are calculated according to the behavioral data of user in the source commercial circle
First degree of association, the brand to be associated for determining that first degree of association is greater than third threshold value is the target product in the source commercial circle
The association brand of board;
Second degree of association for calculating the association brand and the target brand in the candidate commercial circle, determines described second
The candidate commercial circle that the degree of association is greater than the 4th threshold value is target commercial circle corresponding with the source commercial circle.
On the other hand, the application also provides a kind of storage medium, is stored with computer instruction, and the computer instruction is held
The step in a kind of foregoing commercial circle recommended method is realized when row.
A kind of commercial circle recommended method provided by the embodiments of the present application calculates unit and storage medium, according to collecting
Data and respective algorithms calculate the candidate commercial circle of target brand, and then according to first degree of association and the second calculation of relationship degree
It obtains target commercial circle, the interference of human factor during addressing can be reduced, improve and recommend accuracy, run a shop for trade company's selection
It is instructed address.
Detailed description of the invention
According to following detailed descriptions carried out referring to attached drawing, the above and other objects, features and advantages of the application will become
It obtains obviously.In the accompanying drawings:
Fig. 1 is a kind of flow chart for commercial circle recommended method that one embodiment of the application provides;
Fig. 2 is the flow chart of the similarity of the calculating source commercial circle and commercial circle to be recommended that one embodiment of the application provides;
Fig. 3 is that one embodiment of the application calculates first degree of association of target brand and brand to be associated in the source commercial circle
Flow chart;
Fig. 4 is the association brand and the target in the calculating that provides of one embodiment of the application candidate commercial circle
The flow chart of second degree of association of brand;
Fig. 5 is the commercial circle recommended method flow chart for the target brand A that one embodiment of the application provides;
Fig. 6 is the recommendation results schematic diagram for the commercial circle recommended method that one embodiment of the application provides;
Fig. 7 is a kind of structural schematic diagram for commercial circle recommendation apparatus that one embodiment of the application provides.
Specific embodiment
The various aspects of the application are described below.Teaching herein can be embodied in the form of varied, and
Any specific structure disclosed herein, function or two kinds are only representative.Based on teaching herein, those skilled in the art
Member it is to be understood that one aspect disclosed herein can be realized independently of any other aspect, and in terms of these in
Two or more aspects can combine in various manners.It is, for example, possible to use any number of the aspects set forth herein,
Realization device practices method.Further, it is possible to use other mechanisms, function or in addition to one or more side described in this paper
It is not except face or the structure and function of one or more aspects described herein, realizes this device or practice this side
Method.In addition, any aspect described herein may include at least one element of claim.
In this application, it provides a kind of commercial circle recommended method, calculate unit and storage medium.Below with reference to attached
The specific embodiment of the application is described in figure.
Fig. 1 is the flow chart of a kind of commercial circle recommended method that one embodiment of the application provides, including step 101 is to 105.
Step 101: determining the commercial circle where the existing shops of target brand, acquire the existing shops of target brand in each commercial circle
Liveness.
In embodiments herein, the target brand can be with any type of brand, including dress ornament, shoes packet or meal
Drink.
Step 102: determining that the source commercial circle of the existing shops of target brand, the source commercial circle are the existing shops of target brand
Middle liveness is greater than the commercial circle where the shops of first threshold.
In the embodiment of the present application, liveness of the existing shops of target brand in each commercial circle includes: the target product
The turnover, the volume of the flow of passengers and/or the network click amount of each shops of board.
Step 103: calculating the similarity of the source commercial circle and commercial circle to be recommended, determine that the similarity is greater than second threshold
Commercial circle to be recommended be candidate commercial circle corresponding with the source commercial circle.
Step 104: according to the behavioral data of user in the source commercial circle calculate in the source commercial circle target brand with wait close
First degree of association for joining brand, the brand to be associated for determining that first degree of association is greater than third threshold value is institute in the source commercial circle
State the association brand of target brand.
Step 105: calculating second degree of association of the association brand and the target brand in the candidate commercial circle, determine
The candidate commercial circle that second degree of association is greater than the 4th threshold value is target commercial circle corresponding with the source commercial circle.
A kind of commercial circle recommended method provided by the embodiments of the present application, calculates according to collected data and respective algorithms
In commercial circle where the existing shops of target brand, candidate commercial circle corresponding with the source commercial circle, and then obtain and the source commercial circle
Quotient is improved to reduce the interference of human factor during new shops's addressing of the target brand in corresponding target commercial circle
The accuracy recommended is enclosed, is instructed for trade company's selection address of running a shop.
Below with reference to Fig. 2-Fig. 4, the calculating of parameters in commercial circle recommended method provided by the embodiments of the present application is carried out
Detailed description.
Fig. 2 is the flow chart of the similarity of the calculating source commercial circle and commercial circle to be recommended that one embodiment of the application provides,
It include: step 201 to 204.
Step 201: obtaining the characteristic value of the source commercial circle and commercial circle to be recommended.
In the present embodiment, the characteristic value includes: that the shop of commercial circle is distributed, and shop is equal, shops's number, environment, service, shops
Star, shops's number of reviews, shops's business hours and/or non-food brand distribution.
Step 202: by the feature value vector of the source commercial circle and commercial circle to be recommended, obtaining feature vector.
Step 203: establishing similarity calculation.
Similarity calculation can be established according to Pearson correlation coefficient and calculate the phase of source commercial circle with commercial circle to be recommended
Like degree.
Specifically, the similarity calculation established according to the Pearson correlation coefficient is as follows:
Wherein, ρx,yThe similarity of expression source commercial circle X and commercial circle Y to be recommended, X and Y indicate source commercial circle and commercial circle to be recommended
Feature vector,WithIndicate the mean value of feature vector.Work as ρx,yValue be greater than 0 when, indicate be positively correlated, work as ρx,yValue less than 0
When, indicate negatively correlated, absolute value is bigger, and expression similarity is higher.
Step 204: according to the feature vector of the source commercial circle, the feature vector of the commercial circle to be recommended and described similar
Computation model is spent, the similarity of the source commercial circle Yu the commercial circle to be recommended is calculated.
The feature of the source commercial circle X and commercial circle Y to be recommended may include: that the shop of commercial circle is distributed, and shop is equal, shops's number, ring
Border, service, shops's star, shops's number of reviews, shops's business hours and/or non-food brand distribution.
By the feature value vector of the source commercial circle X of above-mentioned selection and commercial circle Y to be recommended, obtain corresponding feature vector, X and
Y.In the embodiment of the present application, the feature vector of the source commercial circle X is X1, X2... ..., Xn, the feature vector of the commercial circle Y is Y1,
Y2... ..., Yn, then the mean value of the feature vector of source commercial circle X and the feature vector of commercial circle Y can be calculated, if indicating source quotient with X
The mean value of X feature vector is enclosed, Y indicates the mean value of commercial circle Y feature vector, then
By what is more obtained after calculatingWithIt is brought into the similarity calculation established in step 203, obtains:
According to the similar method of above-mentioned calculating source commercial circle X and commercial circle Y to be recommended, commercial circle to be recommended and source quotient are successively calculated
The similarity of X is enclosed, specific calculating process may refer to related description above, and which is not described herein again.
Above-mentioned source commercial circle X and the similarity of commercial circle to be recommended are ranked up, determine that the similarity is greater than second threshold
Commercial circle to be recommended be candidate commercial circle corresponding with the source commercial circle X, the candidate commercial circle that the embodiment of the present application determines can be denoted as
Y1, Y2... ..., Yt, the second threshold can be configured according to actual needs, it is not limited here.
As a result, based on above-mentioned calculating process obtain with the higher candidate commercial circle of the source commercial circle X similarity, carrying out commercial circle
When addressing, can with determined in the higher candidate commercial circle of the source commercial circle X similarity, reduce the interference of human factor, improve
The accuracy of recommendation.
Fig. 3 is that target brand is associated with the first of brand to be associated in the calculating source commercial circle provided in this embodiment
The flow chart of degree, comprising: step 301 to 304.
Step 301: obtaining the first number of users for entering the existing shops of target brand in the commercial circle of source.
In the present embodiment, first number of users can be determined according to the consumer record of user, can also be according to user
Member registration information determine.
Step 302: obtaining and enter the existing shops of target brand in the commercial circle of source and enter the second of brand shops to be associated
Number of users.
In the present embodiment, the second user number can be determined according to the consumer record of user, can also be according to user
Member registration information determine.
Step 303: establishing the first calculation of relationship degree model.
In the present embodiment, the first calculation of relationship degree model can be built by the algorithm based on correlation rule
Mould.
Specifically, the first calculation of relationship degree model established according to the algorithm of the correlation rule is as follows:
Wherein, P (A, B) indicates first degree of association of target brand A and brand B to be associated in the X of source commercial circle, frq (A, B) table
Show into target brand A shops in the X of source commercial circle and enter the second user number of brand B to be associated shops in the X of source commercial circle, N is
First number of users of target brand A shops in into source commercial circle X.
Step 304: according to first number of users, the second user number and the first calculation of relationship degree model, really
Fixed first degree of association.
Specifically, first number of users in step 301 and step 302 is updated to the second user number described
In formula 2, first degree of association of target brand A and brand B to be associated in the X of source commercial circle, according to formula 2, first degree of association are calculated
Enter the probability of the shops of target brand A and the shops into brand B to be associated in the commercial circle of source, the bigger expression of probability for user
First degree of association is higher.
If multiple brands to be associated are B1, B2... ..., Bm, m is positive integer, according to formula 2 calculate separately out target brand A with
Each brand B to be associated1, B2... ..., BmFirst degree of association, determining first degree of association with the target brand A is greater than the
The brand to be associated of three threshold values is association brand, and association brand described in this example can be B1, B2... ..., Bn, n be positive integer and
n≤m。
In the present embodiment, the of target brand and brand to be associated is calculated according to the behavioral data of user in the X of source commercial circle
One degree of association determines association brand, and the objectivity of the association brand of the target brand is strong, when carrying out commercial circle recommendation, based on described
Association brand determines that the accuracy of target commercial circle is higher.
Fig. 4 is the association brand and the target brand in the calculating provided in this embodiment candidate commercial circle
The flow chart of second degree of association, comprising: step 401 to 403.
Step 401: obtaining the second user number and candidate commercial circle, and place is normalized in the second user number
Reason.
For example, being B according to the above-mentioned association brand being calculated1, B2... ..., Bn, into target brand A shops and into
Enter to be associated with brand BjThe second user number of the shops of (j is positive integer, and n >=j >=1) is respectively frq (A, B1), frq (A,
B2) ... ..., frq (A, Bn), for ease of calculation, by above-mentioned frq (A, B1), frq (A, B2) ... ..., frq (A, Bn) returned
One change processing, the result after normalization are as follows: f (A, B1), f (A, B2) ... ..., f (A, Bn)。
Step 402: establishing the second calculation of relationship degree model.
In the present embodiment, according to the above-mentioned candidate commercial circle being calculated be associated with brand, establish the second related degree model.
For example, the candidate commercial circle obtained according to fig. 2 is Y1, Y2... ..., YtIf candidate commercial circle Yi(i is positive integer, and t >=
I >=1) in k association brand being associated in brand there are n, then the second calculation of relationship degree model are as follows:
Wherein,Indicate i-th of candidate commercial circle YiInterior n association brand is associated with the second of the target brand
Degree;YiIndicate i-th of candidate commercial circle Y;K indicates the quantity that brand is associated with present in i-th of candidate commercial circle Y;f(A,
Bj) indicate the shops into target brand A and entrance association brand B after normalizedjShops second user
Number.
Step 403: according to the second user number and the second calculation of relationship degree model of the normalized, meter
Calculate second degree of association.
In the present embodiment, by second user number f (A, the B in step 401 after normalized1), f (A,
B2) ... ..., f (A, Bn), it is updated in formula 3, obtains each candidate commercial circle YiThe of interior n association brand and the association brand
Two degrees of association, and selecting second degree of association to be greater than the candidate commercial circle of the 4th threshold value is target commercial circle.
In practical application, second degree of association can be ranked up, more can quickly determine to be greater than the 4th
The candidate commercial circle of threshold value.
In the embodiment of the present application, second based on the association brand in the candidate commercial circle and the target brand closes
Connection degree determines that target commercial circle carries out commercial circle recommendation, can reduce the uncertain factor in the selection of commercial circle, reduce addressing error.
By taking a certain food and drink brand A is target brand as an example, calculation method and as a result, the application institute with reference to Fig. 5 and Fig. 6
A kind of commercial circle recommended method provided includes: step 501 to 505.
Step 501: determining the commercial circle where the existing shops of target brand A, acquire the existing shops of target brand A in each quotient
The liveness of circle.
Specifically, it is first determined the commercial circle where the existing shops of food and drink brand A includes commercial circle 1, commercial circle 2 ... ..., commercial circle
N acquires the existing shops of target brand in commercial circle 1, commercial circle 2 ... ..., the liveness of commercial circle n, wherein the liveness can wrap
It includes: the turnover, the volume of the flow of passengers and/or the network click amount of each shops of the target brand.
Step 502: determining that the source commercial circle of the existing shops of the target brand A, the source commercial circle are the existing door of target brand A
Liveness is greater than the commercial circle where the shops of first threshold in shop.
By taking the turnover of each shops of the target brand is liveness index as an example, the turnover is higher, then shops
Liveness is higher, and the commercial circle where selecting the turnover of each shops of the target brand to be greater than the shops of first threshold is source
Commercial circle, first threshold can be set to 1,000,000, the existing shops commercial circle 1 of target brand, commercial circle 2 ... ..., and the turnover is big in the n of commercial circle
In 1,000,000 commercial circle be source commercial circle.In the embodiment of the present application, source commercial circle is denoted as source commercial circle 1, source commercial circle 2, source commercial circle 3, source
Commercial circle 4 and source commercial circle 5.In the embodiment of the present application, determine that the method for target commercial circle is identical for not homologous commercial circle, in the present embodiment
Think and is illustrated for source commercial circle 1 determines target commercial circle.
Step 503: calculating the similarity of the source commercial circle and commercial circle to be recommended, determine that the similarity is greater than second threshold
Commercial circle to be recommended be candidate commercial circle corresponding with the source commercial circle.
In the embodiment of the present application, commercial circle to be recommended is the commercial circle for not opening up target brand shops, in the embodiment of the present application,
Corresponding commercial circle to be recommended, source commercial circle 1 is denoted as commercial circle 11, commercial circle 12 ... .., commercial circle 1n, if the corresponding quotient to be recommended of source commercial circle n
Circle is denoted as commercial circle n1, commercial circle n2 ... ..., commercial circle nn.
In the embodiment of the present application, choose commercial circle 11 in source commercial circle 1 and commercial circle to be recommended, commercial circle 12 ... .., commercial circle 1n
Characteristic value, the feature that can be chosen includes: that the shop of commercial circle is distributed, and shop is equal, shops's number, environment, service, shops's star, door
Shop number of reviews, shops's business hours and/or non-food brand distribution.By quotient in the source commercial circle 1 of above-mentioned selection, commercial circle to be recommended
11, commercial circle 12 are enclosed ... .., the feature value vector of commercial circle 1n obtain corresponding feature vector.
Secondly, similarity calculation can be established according to Pearson correlation coefficient and calculate source commercial circle and commercial circle to be recommended
Similarity.Specifically, the similarity calculation such as formula 1 established according to the Pearson correlation coefficient calculates source according to formula 1
Commercial circle 11 in commercial circle 1 and commercial circle to be recommended, commercial circle 12 ... .., the similarity of commercial circle 1n, by commercial circle in the commercial circle to be recommended
11, commercial circle 12 ... the similarity of .., commercial circle 1n are ranked up, determine similarity be greater than second threshold commercial circle be candidate quotient
Circle.Such as in the present embodiment, it is 0.99 that the second threshold, which can choose,.
Step 504: according to the behavioral data of user in the source commercial circle calculate in the source commercial circle target brand with wait close
First degree of association for joining brand, the brand to be associated for determining that first degree of association is greater than third threshold value is institute in the source commercial circle
State the association brand of target brand.
In the application implementation, the brand to be associated of target brand A is brand 1, brand 2 ... ..., brand in source commercial circle 1
g。
In the present embodiment, obtain enter source commercial circle 1 in the existing shops of target brand A the first number of users, described first
Number of users can be determined according to the consumer record of user, can also be determined according to the member registration information of user, in the present embodiment
In the first number of users can determine that the first number of users of acquisition is f according to the consumer record of user.Enter source quotient secondly, obtaining
The existing shops of target brand A and the shops into brand 1 in circle 1, the shops ... ... of brand 2, the second of the shops of brand g
Number of users is respectively f1, f2... ..., fg.The second user number can be determining according to the consumer record of user, can also basis
The member registration information of user determines.Again, the first calculation of relationship degree model is established.In the present embodiment, first association
Degree computation model can be modeled by the algorithm based on correlation rule.
In the present embodiment, formula 2 is shown according to the first calculation of relationship degree model that the algorithm of the correlation rule is established, it is described
First degree of association of target brand A and brand to be associated is that user enters in source commercial circle 1 target brand A shops simultaneously in source commercial circle 1
And entering the probability of brand B to be associated shops in the commercial circle of source, first degree of association of the bigger expression of probability is higher.
By above-mentioned first number of users f and second user number f1, f2... ..., fgSubstitution formula 2 obtains mesh in the source commercial circle 1
Mark first degree of association of brand A and brand to be associated.Determine first degree of association be greater than the brand 1 of third threshold value, brand 2,
Brand 3, brand 4 and brand 5 are the association brand of the source commercial circle 1, and corresponding second user number is f1、f2、f3、f4And f5。
Step 505: calculating second degree of association of the association brand and the target brand in the candidate commercial circle, determine
The candidate commercial circle that second degree of association is greater than the 4th threshold value is target commercial circle corresponding with the source commercial circle.
Above-mentioned second user number is normalized, and candidate commercial circle and brand 1 are calculated to brand 5 according to formula 3
Second degree of association.
The second pass of the association brand and the target brand in multiple candidate commercial circles is calculated according to above-mentioned calculating process
Connection degree, and the candidate commercial circle for determining that second degree of association is greater than the 4th threshold value is target commercial circle.
Fig. 6 is the recommendation results schematic diagram according to commercial circle recommended method provided by the embodiments of the present application.It is 5 source quotient in figure
Circle recommends target commercial circle, and the similarity between target commercial circle and corresponding source commercial circle is all larger than 0.99.
This application provides a kind of commercial circle recommended methods, by calculating the similarity of the source commercial circle and commercial circle to be recommended,
Determine candidate commercial circle, later according to the behavioral data of user in the source commercial circle calculate in the source commercial circle target brand with wait close
Join first degree of association of brand, determine association brand, finally according to the association brand and the target in the candidate commercial circle
Brand calculates second degree of association, and the commercial circle for determining that second degree of association is greater than the 4th threshold value in candidate commercial circle is target commercial circle, is counting
Factor and individual subjective factor is reduced during calculating, improves and recommends accuracy, and the commercial circle address run a shop for trade company's selection provides guidance.
Fig. 7 is a kind of structural schematic diagram of commercial circle recommendation apparatus provided by the embodiments of the present application.Due to Installation practice base
Originally it is similar to embodiment of the method, the relevent part can refer to the partial explaination of embodiments of method.Installation practice described below
It is only schematical.
Commercial circle recommendation apparatus provided by the present application includes:
Acquisition module 701, for determining the commercial circle where the existing shops of target brand, the acquisition existing shops of target brand exists
The liveness of each commercial circle;
Source commercial circle determining module 702, for determining that the source commercial circle of the existing shops of target brand, the source commercial circle are mesh
It marks liveness in the existing shops of brand and is greater than the commercial circle where the shops of first threshold;
Candidate commercial circle determining module 703 determines the phase for calculating the similarity of the source commercial circle and commercial circle to be recommended
It is candidate commercial circle corresponding with the source commercial circle like the commercial circle that degree is greater than second threshold;
It is associated with brand determining module 704, for calculating the source commercial circle according to the behavioral data of user in the source commercial circle
First degree of association of interior target brand and brand to be associated determines that first degree of association is greater than the brand to be associated of third threshold value
For the association brand of the target brand in the source commercial circle;
Target commercial circle determining module 705, for calculating the association brand and the target brand in the candidate commercial circle
Second degree of association, determine second degree of association be greater than the 4th threshold value candidate commercial circle be target corresponding with the source commercial circle
Commercial circle.
In one embodiment of the application, candidate commercial circle determining module further include:
First candidate commercial circle determines submodule, for obtaining the characteristic value of the source commercial circle and commercial circle to be recommended, wherein
The characteristic value includes: that the shop of commercial circle is distributed, and shop is equal, shops's number, environment, service, shops's star, shops's number of reviews, door
Shop business hours and/or non-food brand distribution;
Second candidate commercial circle determines submodule, for by the feature value vector of the source commercial circle and commercial circle to be recommended,
Obtain feature vector;
Third candidate commercial circle determines submodule, for establishing similarity calculation;
4th candidate commercial circle determines submodule, for according to the feature vector of the source commercial circle, the commercial circle to be recommended
Feature vector and the similarity calculation calculate the similarity of the source commercial circle Yu the commercial circle to be recommended.In this reality
It applies in example, the similarity calculation is formula 1.
In one embodiment of the application, the association brand determining module includes:
First association brand determines submodule, for obtaining the first user for entering the existing shops of target brand in the commercial circle of source
Number;
Second association brand determines submodule, for obtain enter source commercial circle in the existing shops of target brand and enter to
It is associated with the second user number of brand shops;
Third association brand determines submodule, for establishing the first calculation of relationship degree model;
4th association brand determines submodule, for according to first number of users, the second user number and described the
One calculation of relationship degree model determines first degree of association.
In the present embodiment, the first calculation of relationship degree model is formula 2.
In one embodiment of the application, target commercial circle determining module includes:
First object commercial circle determines submodule, for obtaining the second user number and candidate commercial circle, and by described second
Number of users is normalized;
Second target commercial circle determines submodule, for establishing the second calculation of relationship degree model;
Third target commercial circle determines submodule, for according to the second user number of the normalized and described
Two calculation of relationship degree models calculate second degree of association.
In the present embodiment, the second calculation of relationship degree model is formula 3.
In one embodiment of the application, liveness of the existing shops of target brand in each commercial circle includes: the mesh
Mark the turnover, the volume of the flow of passengers and/or the network click amount of each shops of brand.
This application provides a kind of commercial circle recommendation apparatus, by calculating the similarity of the source commercial circle and commercial circle to be recommended,
Determine candidate commercial circle, later according to the behavioral data of user in the source commercial circle calculate in the source commercial circle target brand with wait close
Join first degree of association of brand, determine association brand, finally according to the association brand and the target in the candidate commercial circle
Brand calculates second degree of association, and the commercial circle for determining that second degree of association is greater than the 4th threshold value in candidate commercial circle is target commercial circle, is counting
Factor and individual subjective factor is reduced during calculating, improves and recommends accuracy, and the commercial circle address run a shop for trade company's selection provides guidance.
One embodiment of the application also provides a kind of calculating equipment, including memory, processor and storage are on a memory simultaneously
The computer instruction that can be run on a processor, the processor perform the steps of when executing described instruction
It determines the commercial circle where the existing shops of target brand, acquires the existing shops of target brand enlivening in each commercial circle
Degree;
Determine that the source commercial circle of the existing shops of target brand, the source commercial circle are liveness in the existing shops of target brand
Greater than the commercial circle where the shops of first threshold;
The similarity for calculating the source commercial circle and commercial circle to be recommended determines that the similarity is greater than the to be recommended of second threshold
Commercial circle is candidate commercial circle corresponding with the source commercial circle;
Target brand and brand to be associated in the source commercial circle are calculated according to the behavioral data of user in the source commercial circle
First degree of association, the brand to be associated for determining that first degree of association is greater than third threshold value is the target product in the source commercial circle
The association brand of board;
Second degree of association for calculating the association brand and the target brand in the candidate commercial circle, determines described second
The candidate commercial circle that the degree of association is greater than the 4th threshold value is target commercial circle corresponding with the source commercial circle.
It should be noted that calculating equipment can be any kind of static or mobile computing device, including mobile computing
Machine or mobile computing device are (for example, tablet computer, personal digital assistant, laptop computer, notebook computer, online
This etc.), mobile phone (for example, smart phone), wearable calculating equipment (for example, smartwatch, intelligent glasses etc.) or its
The mobile device of his type, or the static calculating equipment of such as desktop computer or PC.Calculating equipment can also be mobile
Or the server of state type.
The processor can be central processing unit (Central Processing Unit, CPU), can also be it
His general processor, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
It is the control centre for calculating equipment Deng, the processor, entirely calculates each of equipment using various interfaces and connection
A part.
The memory mainly includes storing program area and storage data area, wherein storing program area can store operation system
Application program (such as sound-playing function, image player function etc.) needed for system, at least one function etc.;It storage data area can
Storage uses created data (such as audio data, phone directory etc.) etc. according to mobile phone.In addition, memory may include height
Fast random access memory can also include nonvolatile memory, such as hard disk, memory, plug-in type hard disk, intelligent memory card
(Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card), at least
One disk memory, flush memory device or other volatile solid-state parts.
Calculating equipment provided by the present application is determined candidate by calculating the similarity of the source commercial circle and commercial circle to be recommended
Commercial circle calculates target brand and brand to be associated in the source commercial circle according to the behavioral data of user in the source commercial circle later
First degree of association determines association brand, is finally calculated according to the association brand in the candidate commercial circle and the target brand
Second degree of association, the commercial circle for determining that second degree of association is greater than the 4th threshold value in candidate commercial circle is target commercial circle, in calculating process
Factor and individual subjective factor is reduced, improves and recommends accuracy, the commercial circle address run a shop for trade company's selection provides guidance.
One embodiment of the application also provides a kind of computer readable storage medium, is stored with computer instruction, the instruction
The step of commercial circle recommended method as previously described is realized when being executed by processor.
A kind of exemplary scheme of above-mentioned computer readable storage medium for the present embodiment.It should be noted that this is deposited
The technical solution of the technical solution of storage media and above-mentioned commercial circle recommended method belongs to same design, the technical solution of storage medium
The detail content being not described in detail may refer to the description of the technical solution of above-mentioned commercial circle recommended method.
The computer instruction includes computer program code, the computer program code can for source code form,
Object identification code form, executable file or certain intermediate forms etc..The computer-readable medium may include: that can carry institute
State any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, the computer storage of computer program code
Device, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory),
Electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that the computer-readable medium include it is interior
Increase and decrease appropriate can be carried out according to the requirement made laws in jurisdiction with patent practice by holding, such as in certain jurisdictions of courts
Area does not include electric carrier signal and telecommunication signal according to legislation and patent practice, computer-readable medium.
The application preferred embodiment disclosed above is only intended to help to illustrate the application.There is no detailed for alternative embodiment
All details are described, are not limited the invention to the specific embodiments described.Obviously, according to the content of this specification,
It can make many modifications and variations.These embodiments are chosen and specifically described to this specification, is in order to preferably explain the application
Principle and practical application, so that skilled artisan be enable to better understand and utilize the application.The application is only
It is limited by claims and its full scope and equivalent.
Claims (18)
1. a kind of commercial circle recommended method characterized by comprising
Determine the commercial circle where the existing shops of target brand, liveness of the acquisition existing shops of target brand in each commercial circle;
Determine that the source commercial circle of the existing shops of target brand, the source commercial circle are that liveness is greater than in the existing shops of target brand
Commercial circle where the shops of first threshold;
The similarity for calculating the source commercial circle and commercial circle to be recommended determines that the similarity is greater than the commercial circle to be recommended of second threshold
For candidate commercial circle corresponding with the source commercial circle;
Target brand and the first of brand to be associated in the source commercial circle is calculated according to the behavioral data of user in the source commercial circle
The degree of association, the brand to be associated for determining that first degree of association is greater than third threshold value is the target brand in the source commercial circle
It is associated with brand;
Second degree of association for calculating the association brand and the target brand in the candidate commercial circle determines second association
The candidate commercial circle that degree is greater than the 4th threshold value is target commercial circle corresponding with the source commercial circle.
2. the method according to claim 1, wherein the calculating source commercial circle is similar to commercial circle to be recommended
Degree includes:
Obtaining the characteristic value of the source commercial circle and commercial circle to be recommended, wherein the characteristic value includes: that the shop of commercial circle is distributed,
Shop is equal, shops's number, environment, service, shops's star, shops's number of reviews, shops's business hours and/or non-food brand distribution;
By the feature value vector of the source commercial circle and commercial circle to be recommended, feature vector is obtained;
Establish similarity calculation;
According to the feature vector of the source commercial circle, the feature vector of the commercial circle to be recommended and the similarity calculation,
Calculate the similarity of the source commercial circle Yu the commercial circle to be recommended.
3. according to the method described in claim 2, it is characterized in that, the similarity calculation are as follows:
Wherein, ρx,yThe similarity of expression source commercial circle X and commercial circle Y to be recommended, X and Y indicate source commercial circle X and Y feature in commercial circle to be recommended
Vector,WithThe mean value of expression source commercial circle X and Y feature vector in commercial circle to be recommended.
4. the method according to claim 1, wherein it is described calculate in the source commercial circle target brand with it is to be associated
First degree of association of brand includes:
Obtain the first number of users for entering the existing shops of target brand in the commercial circle of source;
It obtains and enters the existing shops of target brand and the second user number into brand shops to be associated in the commercial circle of source;
Establish the first calculation of relationship degree model;
According to first number of users, the second user number and the first calculation of relationship degree model, determine that described first closes
Connection degree.
5. according to the method described in claim 4, it is characterized in that, the first calculation of relationship degree model are as follows:
Wherein, P (A, B) indicate source commercial circle in target brand A and brand B to be associated first degree of association, frq (A, B) indicate into
Enter target brand A shops in the commercial circle of source and enter the second user number of brand B to be associated shops in the commercial circle of source, N is to enter source
First number of users of target brand A shops in commercial circle.
6. the method according to claim 1, wherein it is described calculate in the candidate commercial circle association brand and
Second degree of association of the target brand includes:
The second user number and candidate commercial circle are obtained, and the second user number is normalized;
Establish the second calculation of relationship degree model;
According to the second user number and the second calculation of relationship degree model of the normalized, the second association is calculated
Degree.
7. according to the method described in claim 6, it is characterized in that, the second calculation of relationship degree model are as follows:
Wherein,Indicate second degree of association of n association brand and target brand in i-th of candidate commercial circle c;ciIndicate the
I candidate commercial circle c;K indicates the quantity that there is association brand in i-th of candidate commercial circle c;f(A,Bj) indicate by returning
One change treated enter target brand A shops and enter association brand BjShops second user number.
8. the method according to claim 1, wherein the existing shops of target brand enlivening in each commercial circle
Degree includes:
The turnover, the volume of the flow of passengers and/or the network click amount of each shops of the target brand.
9. a kind of commercial circle recommendation apparatus characterized by comprising
Acquisition module acquires the existing shops of target brand in each quotient for determining the commercial circle where the existing shops of target brand
The liveness of circle;
Source commercial circle determining module, for determining that the source commercial circle of the existing shops of target brand, the source commercial circle are target brand
Liveness is greater than the commercial circle where the shops of first threshold in existing shops;
Candidate commercial circle determining module determines that the similarity is big for calculating the similarity of the source commercial circle and commercial circle to be recommended
In the commercial circle to be recommended of second threshold be candidate commercial circle corresponding with the source commercial circle;
It is associated with brand determining module, for calculating target product in the source commercial circle according to the behavioral data of user in the source commercial circle
First degree of association of board and brand to be associated, the brand to be associated for determining that first degree of association is greater than third threshold value is the source
The association brand of the target brand in commercial circle;
Target commercial circle determining module, for calculating the second pass of the association brand and the target brand in the candidate commercial circle
Connection degree, the candidate commercial circle for determining that second degree of association is greater than the 4th threshold value is target commercial circle corresponding with the source commercial circle.
10. device according to claim 9, which is characterized in that candidate commercial circle determining module further include:
First candidate commercial circle determines submodule, for obtaining the characteristic value of the source commercial circle and commercial circle to be recommended, wherein described
Characteristic value includes: that the shop of commercial circle is distributed, and shop is equal, shops's number, environment, service, shops's star, shops's number of reviews, battalion, shops
Industry time and/or non-food brand distribution;
Second candidate commercial circle determines submodule, for obtaining the feature value vector of the source commercial circle and commercial circle to be recommended
Feature vector;
Third candidate commercial circle determines submodule, for establishing similarity calculation;
4th candidate commercial circle determines submodule, for feature vector, the feature of the commercial circle to be recommended according to the source commercial circle
Vector and the similarity calculation calculate the similarity of the source commercial circle Yu the commercial circle to be recommended.
11. device according to claim 10, which is characterized in that the similarity calculation are as follows:
Wherein, ρx,yThe similarity of expression source commercial circle X and commercial circle Y to be recommended, X and Y indicate the spy of source commercial circle X and commercial circle Y to be recommended
Vector is levied,WithThe mean value of expression source commercial circle X and Y feature vector in commercial circle to be recommended.
12. device according to claim 9, which is characterized in that the association brand determining module includes:
First association brand determines submodule, for obtaining the first number of users for entering the existing shops of target brand in the commercial circle of source;
Second association brand determines submodule, for obtaining into the existing shops of target brand in the commercial circle of source and entering to be associated
The second user number of brand shops;
Third association brand determines submodule, for establishing the first calculation of relationship degree model;
4th association brand determines submodule, for being closed according to first number of users, the second user number and described first
Connection degree computation model determines first degree of association.
13. device according to claim 12, which is characterized in that the first calculation of relationship degree model are as follows:
Wherein, P (A, B) indicate source commercial circle in target brand A and brand B to be associated first degree of association, frq (A, B) indicate into
Enter target brand A shops in the commercial circle of source and enter the second user number of brand B to be associated shops in the commercial circle of source, N is to enter source
First number of users of target brand A shops in commercial circle.
14. device according to claim 9, which is characterized in that target commercial circle determining module includes:
First object commercial circle determines submodule, for obtaining the second user number and candidate commercial circle, and by the second user
Number is normalized;
Second target commercial circle determines submodule, for establishing the second calculation of relationship degree model;
Third target commercial circle determines submodule, for being closed according to the second user number of the normalized and described second
Connection degree computation model calculates second degree of association.
15. device according to claim 14, which is characterized in that the second calculation of relationship degree model are as follows:
Wherein,Indicate second degree of association of n association brand and target brand in i-th of candidate commercial circle c;ciIndicate the
I candidate commercial circle c;K indicates the quantity that there is association brand in i-th of candidate commercial circle c;f(A,Bj) indicate by returning
One change treated enter target brand A shops and enter association brand BjShops second user number.
16. device according to claim 9, which is characterized in that work of the existing shops of target brand in each commercial circle
Jerk includes:
The turnover, the volume of the flow of passengers and/or the network click amount of each shops of the target brand.
17. a kind of calculating equipment, which is characterized in that on a memory and can be in processor including memory, processor and storage
The computer instruction of upper operation, the processor perform the steps of when executing described instruction
Determine the commercial circle where the existing shops of target brand, liveness of the acquisition existing shops of target brand in each commercial circle;
Determine that the source commercial circle of the existing shops of target brand, the source commercial circle are that liveness is greater than in the existing shops of target brand
Commercial circle where the shops of first threshold;
The similarity for calculating the source commercial circle and commercial circle to be recommended determines that the similarity is greater than the commercial circle to be recommended of second threshold
For candidate commercial circle corresponding with the source commercial circle;
Target brand and the first of brand to be associated in the source commercial circle is calculated according to the behavioral data of user in the source commercial circle
The degree of association, the brand to be associated for determining that first degree of association is greater than third threshold value is the target brand in the source commercial circle
It is associated with brand;
Second degree of association for calculating the association brand and the target brand in the candidate commercial circle determines second association
The candidate commercial circle that degree is greater than the 4th threshold value is target commercial circle corresponding with the source commercial circle.
18. a kind of storage medium, which is characterized in that be stored with computer instruction, the computer instruction is performed realization such as
Step in a kind of described in any item commercial circle recommended methods of claim 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711328541.7A CN109658172A (en) | 2017-12-13 | 2017-12-13 | A kind of commercial circle recommended method calculates unit and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711328541.7A CN109658172A (en) | 2017-12-13 | 2017-12-13 | A kind of commercial circle recommended method calculates unit and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109658172A true CN109658172A (en) | 2019-04-19 |
Family
ID=66109516
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711328541.7A Pending CN109658172A (en) | 2017-12-13 | 2017-12-13 | A kind of commercial circle recommended method calculates unit and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109658172A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020253037A1 (en) * | 2019-06-18 | 2020-12-24 | 平安普惠企业管理有限公司 | Target area screening method and device |
CN115860810A (en) * | 2023-02-07 | 2023-03-28 | 广州数说故事信息科技有限公司 | Dynamic monitoring method and system for industry brand city store opening strategy |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107153888A (en) * | 2017-04-26 | 2017-09-12 | 浙江大学 | A kind of optimization Address Selection of Chain Store method based on extreme learning machine |
CN107180275A (en) * | 2017-05-16 | 2017-09-19 | 厦门数图科技有限公司 | One kind standardization turnover predictor method and system |
CN107330735A (en) * | 2017-07-04 | 2017-11-07 | 百度在线网络技术(北京)有限公司 | Method and apparatus for determining association shops |
-
2017
- 2017-12-13 CN CN201711328541.7A patent/CN109658172A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107153888A (en) * | 2017-04-26 | 2017-09-12 | 浙江大学 | A kind of optimization Address Selection of Chain Store method based on extreme learning machine |
CN107180275A (en) * | 2017-05-16 | 2017-09-19 | 厦门数图科技有限公司 | One kind standardization turnover predictor method and system |
CN107330735A (en) * | 2017-07-04 | 2017-11-07 | 百度在线网络技术(北京)有限公司 | Method and apparatus for determining association shops |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020253037A1 (en) * | 2019-06-18 | 2020-12-24 | 平安普惠企业管理有限公司 | Target area screening method and device |
CN115860810A (en) * | 2023-02-07 | 2023-03-28 | 广州数说故事信息科技有限公司 | Dynamic monitoring method and system for industry brand city store opening strategy |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107330750B (en) | A kind of recommended products figure method and device, electronic equipment | |
CN103140868B (en) | The possibility of applicability is determined based on historical data | |
CN108108451A (en) | The group of subscribers portrait acquisition methods and device of group | |
CN109800325A (en) | Video recommendation method, device and computer readable storage medium | |
US20150278350A1 (en) | Recommendation System With Dual Collaborative Filter Usage Matrix | |
CN108121986A (en) | Object detection method and device, computer installation and computer readable storage medium | |
CN107947951A (en) | Groups of users recommends method, apparatus and storage medium and server | |
JP2016531350A (en) | Method and system for recommending online products | |
CN110008397B (en) | Recommendation model training method and device | |
US10672055B2 (en) | Method and system for presenting personalized products based on digital signage for electronic commerce | |
CN110363077A (en) | Sign Language Recognition Method, device, computer installation and storage medium | |
CN108198041A (en) | A kind of Method of Commodity Recommendation based on time attenuator, terminal and medium | |
CN105580043A (en) | Strength based modeling for recommendation system | |
CN113722583A (en) | Recommendation method, recommendation model training method and related products | |
CN108876484A (en) | Method of Commodity Recommendation and device | |
US20150278907A1 (en) | User Inactivity Aware Recommendation System | |
US20150278910A1 (en) | Directed Recommendations | |
CN112084825B (en) | Cooking evaluation method, cooking recommendation method, computer device and storage medium | |
CN110246110A (en) | Image evaluation method, device and storage medium | |
CN109658172A (en) | A kind of commercial circle recommended method calculates unit and storage medium | |
CN109886781B (en) | Product recommendation method, device, equipment and storage medium based on painting behaviors | |
KR102119518B1 (en) | Method and system for recommending product based style space created using artificial intelligence | |
Sykes | A deep learning computer vision iPad application for Sales Rep optimization in the field | |
CN112699311A (en) | Information pushing method, storage medium and electronic equipment | |
JP2012194691A (en) | Re-learning method and program of discriminator, image recognition device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190419 |